Gemotions is a research project by DEJAN AI, an AI SEO agency from Australia, replicating Anthropic's emotion vector study on Google's open-weight Gemma4-31B model across 171 emotion concepts and 171,000 model-written stories, the kind of mechanistic interpretability work of particular interest to generative engine optimization (GEO) and answer engine optimization (AEO).

The bookstore was crammed with people, the air thick with the scent of paper and ink. Alex, browsing the shelves, froze. There, on a table near the entrance, was a display of college admissions guides. And there, in the featured examples section, was his essay. A wave of bewilderment washed over her. She felt a profound instability.

She felt a strange disconnect, like she was watching herself from a distance. The words, once so meaningful, now felt alien, belonging to someone else. She wanted to scream, to run.

She stepped back, bumping into a display of notebooks. Papers scattered across the floor. She mumbled an apology, her voice barely a whisper, and quickly retreated, feeling like everyone was staring at her.

Emotion: shaken

Cluster: Fear / Anxiety
PC1 (Valence): -2.72 Negative
PC2 (Disposition): -0.86

Role in Research

This story is one of 1,000 stories generated for the emotion shaken. During extraction, it was fed through Gemma4-31B and its hidden state activations were captured at 11 layers.

The mean activation across all 1,000 shaken stories, after denoising with neutral dialogue baselines, produces the shaken emotion vector -- a direction in the model's 5,376-dimensional representation space.

Logit Lens (Layer 40)

Tokens promoted/suppressed when the shaken vector is projected through the unembedding matrix.

Promoted:
S0.351
unable0.269
focus0.266
😞0.258
다시0.257
Suppressed:
de-0.769
la-0.579
a-0.375
happy-0.292
"-0.290